Scholars@Duke
Daniel Reker

Daniel Reker

Assistant Professor of Biomedical Engineering
Biomedical Engineering

Selected Publications

Taking a deep dive with active learning for drug discovery.

Journal Article Nature computational science · October 2024 Full text Cite

Yoked learning in molecular data science

Journal Article Artificial Intelligence in the Life Sciences · June 1, 2024 Active machine learning is an established and increasingly popular experimental design technique where the machine learning model can request additional data to improve the model's predictive performance. It is generally assumed that this data is optimal f ... Full text Cite

A large-scale machine learning analysis of inorganic nanoparticles in preclinical cancer research.

Journal Article Nature nanotechnology · June 2024 Owing to their distinct physical and chemical properties, inorganic nanoparticles (NPs) have shown promising results in preclinical cancer therapy, but designing and engineering them for effective therapeutic purposes remains a challenge. Although a compre ... Full text Cite

The landscape of small-molecule prodrugs.

Journal Article Nat Rev Drug Discov · May 2024 Prodrugs are derivatives with superior properties compared with the parent active pharmaceutical ingredient (API), which undergo biotransformation after administration to generate the API in situ. Although sharing this general characteristic, prodrugs enco ... Full text Link to item Cite

Silk Fibroin-Based Coatings for Pancreatin-Dependent Drug Delivery.

Journal Article Journal of pharmaceutical sciences · March 2024 Triggerable coatings, such as pH-responsive polymethacrylate copolymers, can be used to protect the active pharmaceutical ingredients contained within oral solid dosage forms from the acidic gastric environment and to facilitate drug delivery directly to t ... Full text Cite

Screening oral drugs for their interactions with the intestinal transportome via porcine tissue explants and machine learning.

Journal Article Nature biomedical engineering · March 2024 In vitro systems that accurately model in vivo conditions in the gastrointestinal tract may aid the development of oral drugs with greater bioavailability. Here we show that the interaction profiles between drugs and intestinal drug transporters can be obt ... Full text Cite

Characterizing emerging companies in computational drug development.

Journal Article Nature computational science · February 2024 Computation promises to accelerate, de-risk and optimize drug research and development. An increasing number of companies have entered this space, specializing in the design of new algorithms, computing on proprietary data, and/or development of hardware t ... Full text Cite

Finding the most potent compounds using active learning on molecular pairs.

Journal Article Beilstein journal of organic chemistry · January 2024 Active learning allows algorithms to steer iterative experimentation to accelerate and de-risk molecular optimizations, but actively trained models might still exhibit poor performance during early project stages where the training data is limited and mode ... Full text Cite

Artificial intelligence for natural product drug discovery.

Journal Article Nature reviews. Drug discovery · November 2023 Developments in computational omics technologies have provided new means to access the hidden diversity of natural products, unearthing new potential for drug discovery. In parallel, artificial intelligence approaches such as machine learning have led to e ... Full text Cite

DeepDelta: predicting ADMET improvements of molecular derivatives with deep learning.

Journal Article Journal of cheminformatics · October 2023 Established molecular machine learning models process individual molecules as inputs to predict their biological, chemical, or physical properties. However, such algorithms require large datasets and have not been optimized to predict property differences ... Full text Cite

Improving molecular machine learning through adaptive subsampling with active learning

Journal Article Digital Discovery · August 1, 2023 Data subsampling is an established machine learning pre-processing technique to reduce bias in datasets. However, subsampling can lead to the removal of crucial information from the data and thereby decrease performance. Multiple different subsampling stra ... Full text Cite

Interpretable Molecular Property Predictions Using Marginalized Graph Kernels.

Journal Article Journal of chemical information and modeling · August 2023 Marginalized graph kernels have shown competitive performance in molecular machine learning tasks but currently lack measures of interpretability, which are important to improve trust in the models, detect biases, and inform molecular optimization campaign ... Full text Cite

Oral mRNA delivery using capsule-mediated gastrointestinal tissue injections

Journal Article Matter · March 2, 2022 Nucleic acids are enabling a new generation of therapeutics and vaccines to treat and prevent a range of diseases. While these therapies have typically been limited to parenteral dosing, patients and clinicians prefer oral dosage forms. Furthermore, oral d ... Full text Cite

Dynamic Monitoring of Systemic Biomarkers with Gastric Sensors.

Journal Article Advanced science (Weinheim, Baden-Wurttemberg, Germany) · December 2021 Continuous monitoring in the intensive care setting has transformed the capacity to rapidly respond with interventions for patients in extremis. Noninvasive monitoring has generally been limited to transdermal or intravascular systems coupled to transducer ... Full text Cite

Diagnosing capillary leak in critically ill patients: development of an innovative scoring instrument for non-invasive detection.

Journal Article Annals of intensive care · December 2021 BackgroundThe concomitant occurrence of the symptoms intravascular hypovolemia, peripheral edema and hemodynamic instability is typically named Capillary Leak Syndrome (CLS) and often occurs in surgical critical ill patients. However, neither a un ... Full text Cite

Combating small-molecule aggregation with machine learning

Journal Article Cell Reports Physical Science · September 22, 2021 Biological screens are plagued by false-positive hits resulting from aggregation. Methods to triage small colloidally aggregating molecules (SCAMs) are in high demand. Herein, we disclose a neural network to flag such entities. Our data demonstrate the uti ... Full text Cite

Computationally guided high-throughput design of self-assembling drug nanoparticles.

Journal Article Nature nanotechnology · June 2021 Nanoformulations of therapeutic drugs are transforming our ability to effectively deliver and treat a myriad of conditions. Often, however, they are complex to produce and exhibit low drug loading, except for nanoparticles formed via co-assembly of drugs a ... Full text Cite

Chapter 14: Active Learning for Drug Discovery and Automated Data Curation

Chapter · January 1, 2021 Active machine learning is an experimental design approach that puts machine learning models in the driver seat of data acquisition and automated optimization. Introduced to drug discovery approximately 15 years ago, a handful of impressive studies have re ... Full text Cite

Adaptive Optimization of Chemical Reactions with Minimal Experimental Information

Journal Article Cell Reports Physical Science · November 18, 2020 Optimizing reaction conditions depends on expert chemistry knowledge and laborious exploration of reaction parameters. To automate this task and augment chemical intuition, we here report a computational tool to navigate search spaces. Our approach (LabMat ... Full text Cite

Historical Evolution and Provider Awareness of Inactive Ingredients in Oral Medications.

Journal Article Pharmaceutical research · October 2020 PurposeA multitude of different versions of the same medication with different inactive ingredients are currently available. It has not been quantified how this has evolved historically. Furthermore, it is unknown whether healthcare professionals ... Full text Cite

Artificial intelligence in chemistry and drug design.

Journal Article Journal of computer-aided molecular design · July 2020 Full text Cite

Robotically handled whole-tissue culture system for the screening of oral drug formulations.

Journal Article Nature biomedical engineering · May 2020 Monolayers of cancer-derived cell lines are widely used in the modelling of the gastrointestinal (GI) absorption of drugs and in oral drug development. However, they do not generally predict drug absorption in vivo. Here, we report a robotically handled sy ... Full text Cite

Machine Learning Uncovers Food- and Excipient-Drug Interactions.

Journal Article Cell reports · March 2020 Inactive ingredients and generally recognized as safe compounds are regarded by the US Food and Drug Administration (FDA) as benign for human consumption within specified dose ranges, but a growing body of research has revealed that many inactive ingredien ... Full text Cite

Practical considerations for active machine learning in drug discovery.

Journal Article Drug discovery today. Technologies · December 2019 Active machine learning enables the automated selection of the most valuable next experiments to improve predictive modelling and hasten active retrieval in drug discovery. Although a long established theoretical concept and introduced to drug discovery ap ... Full text Cite

Advanced Editorial to announce a JCAMD Special Issue on Artificial Intelligence and Machine Learning.

Journal Article Journal of computer-aided molecular design · November 2019 Full text Cite

Predicting protein-ligand interactions based on bow-pharmacological space and Bayesian additive regression trees.

Journal Article Scientific reports · May 2019 Identifying potential protein-ligand interactions is central to the field of drug discovery as it facilitates the identification of potential novel drug leads, contributes to advancement from hits to leads, predicts potential off-target explanations for si ... Full text Cite

Computational advances in combating colloidal aggregation in drug discovery.

Journal Article Nature chemistry · May 2019 Small molecule effectors are essential for drug discovery. Specific molecular recognition, reversible binding and dose-dependency are usually key requirements to ensure utility of a novel chemical entity. However, artefactual frequent-hitter and assay inte ... Full text Cite

"Inactive" ingredients in oral medications.

Journal Article Science translational medicine · March 2019 Oral forms of medications contain "inactive" ingredients to enhance their physical properties. Using data analytics, we characterized the abundance and complexity of inactive ingredients in approved medications. A majority of medications contain ingredient ... Full text Cite

Computationally guided high-throughput design of self-assembling drug nanoparticles

Journal Article · 2019 Nanoformulations are transforming our capacity to effectively deliver and treat a myriad of conditions. However, many nanoformulation approaches still suffer from high production complexity and low drug loading. One potential solution relies on harnessing ... Full text Cite

Cheminformatic Analysis of Natural Product Fragments.

Chapter · January 2019 Fragment-like natural products play a pivotal role in natural product research given their improved synthetic and computational tractability as well as commercial availability compared to more complex natural product structures. A multitude of computationa ... Full text Cite

Selection of Informative Examples in Chemogenomic Datasets.

Chapter · January 2018 High-throughput and high-content screening campaigns have resulted in the creation of large chemogenomic matrices. These matrices form the training data which is used to build ligand-target interaction models for pharmacological and chemical biology resear ... Full text Cite

Active learning for computational chemogenomics.

Journal Article Future medicinal chemistry · March 2017 AimComputational chemogenomics models the compound-protein interaction space, typically for drug discovery, where existing methods predominantly either incorporate increasing numbers of bioactivity samples or focus on specific subfamilies of prote ... Full text Cite

Matrix-based Molecular Descriptors for Prospective Virtual Compound Screening.

Journal Article Molecular informatics · January 2017 Molecular descriptors capture diverse structural information of molecules and are a prerequisite for ligand-based similarity searching. In this study, we introduce topological matrix-based descriptors to virtual screening for hit discovery. We evaluated th ... Full text Cite

New use of an old drug: inhibition of breast cancer stem cells by benztropine mesylate.

Journal Article Oncotarget · January 2017 Cancer stem cells (CSCs) play major roles in cancer initiation, metastasis, recurrence and therapeutic resistance. Targeting CSCs represents a promising strategy for cancer treatment. The purpose of this study was to identify selective inhibitors of breast ... Full text Cite

Deorphaning the Macromolecular Targets of the Natural Anticancer Compound Doliculide.

Journal Article Angewandte Chemie (International ed. in English) · September 2016 The cyclodepsipeptide doliculide is a marine natural product with strong actin-polymerizing and anticancer activities. Evidence for doliculide acting as a potent and subtype-selective antagonist of prostanoid E receptor 3 (EP3) is presented. Computational ... Full text Cite

Counting on natural products for drug design.

Journal Article Nature chemistry · June 2016 Natural products and their molecular frameworks have a long tradition as valuable starting points for medicinal chemistry and drug discovery. Recently, there has been a revitalization of interest in the inclusion of these chemotypes in compound collections ... Full text Cite

Multi-objective active machine learning rapidly improves structure-activity models and reveals new protein-protein interaction inhibitors.

Journal Article Chemical science · June 2016 Active machine learning puts artificial intelligence in charge of a sequential, feedback-driven discovery process. We present the application of a multi-objective active learning scheme for identifying small molecules that inhibit the protein-protein inter ... Full text Cite

Spotting and designing promiscuous ligands for drug discovery.

Journal Article Chemical communications (Cambridge, England) · January 2016 The promiscuous binding behavior of bioactive compounds forms a mechanistic basis for understanding polypharmacological drug action. We present the development and prospective application of a computational tool for identifying potential promiscuous drug-l ... Full text Cite

De Novo Fragment Design for Drug Discovery and Chemical Biology.

Journal Article Angewandte Chemie (International ed. in English) · December 2015 Automated molecular de novo design led to the discovery of an innovative inhibitor of death-associated protein kinase 3 (DAPK3). An unprecedented crystal structure of the inactive DAPK3 homodimer shows the fragment-like hit bound to the ATP pocket. Target ... Full text Cite

Revealing the Macromolecular Targets of Fragment-Like Natural Products.

Journal Article Angewandte Chemie (International ed. in English) · September 2015 Fragment-like natural products were identified as ligand-efficient chemical matter for hit-to-lead development and chemical-probe discovery. Relying on a computational method using a topological pharmacophore descriptor and a drug database, several macromo ... Full text Cite

Fragment-Based De Novo Design Reveals a Small-Molecule Inhibitor of Helicobacter Pylori HtrA.

Journal Article Angewandte Chemie (International ed. in English) · August 2015 Sustained identification of innovative chemical entities is key for the success of chemical biology and drug discovery. We report the fragment-based, computer-assisted de novo design of a small molecule inhibiting Helicobacter pylori HtrA protease. Molecul ... Full text Cite

Active-learning strategies in computer-assisted drug discovery.

Journal Article Drug discovery today · April 2015 High-throughput compound screening is time and resource consuming, and considerable effort is invested into screening compound libraries, profiling, and selecting the most promising candidates for further testing. Active-learning methods assist the selecti ... Full text Cite

Chemography of natural product space.

Journal Article Planta medica · April 2015 We present the application of the generative topographic map algorithm to visualize the chemical space populated by natural products and synthetic drugs. Generative topographic maps may be used for nonlinear dimensionality reduction and probabilistic model ... Full text Cite

Multidimensional de novo design reveals 5-HT2B receptor-selective ligands.

Journal Article Angewandte Chemie (International ed. in English) · January 2015 We report a multi-objective de novo design study driven by synthetic tractability and aimed at the prioritization of computer-generated 5-HT2B receptor ligands with accurately predicted target-binding affinities. Relying on quantitative bioactivity models ... Full text Cite

Revealing the macromolecular targets of complex natural products.

Journal Article Nature chemistry · December 2014 Natural products have long been a source of useful biological activity for the development of new drugs. Their macromolecular targets are, however, largely unknown, which hampers rational drug design and optimization. Here we present the development and ex ... Full text Cite

Coping with polypharmacology by computational medicinal chemistry.

Journal Article Chimia · September 2014 Predicting the macromolecular targets of drug-like molecules has become everyday practice in medicinal chemistry. We present an overview of our recent research activities in the area of polypharmacology-guided drug design. A focus is put on the self-organi ... Full text Cite

Deorphaning pyrrolopyrazines as potent multi-target antimalarial agents.

Journal Article Angewandte Chemie (International ed. in English) · July 2014 The discovery of pyrrolopyrazines as potent antimalarial agents is presented, with the most effective compounds exhibiting EC50 values in the low nanomolar range against asexual blood stages of Plasmodium falciparum in human red blood cells, and Plasmodium ... Full text Cite

Identifying the macromolecular targets of de novo-designed chemical entities through self-organizing map consensus.

Journal Article Proceedings of the National Academy of Sciences of the United States of America · March 2014 De novo molecular design and in silico prediction of polypharmacological profiles are emerging research topics that will profoundly affect the future of drug discovery and chemical biology. The goal is to identify the macromolecular targets of new chemical ... Full text Cite

Common non-epigenetic drugs as epigenetic modulators.

Journal Article Trends in molecular medicine · December 2013 Epigenetic effects are exerted by a variety of factors and evidence increases that common drugs such as opioids, cannabinoids, valproic acid, or cytostatics may induce alterations in DNA methylation patterns or histone conformations. These effects occur vi ... Full text Cite

De novo design and optimization of Aurora A kinase inhibitors

Journal Article Chemical Science · March 1, 2013 Drug discovery programs urgently seek new chemical entities that meet the needs of a demanding pharmaceutical industry. Consequently, de novo ligand design is currently re-emerging as a novelty-generating approach. Using ligand-based de novo design softwar ... Full text Cite

Bioinformatic challenges in targeted proteomics.

Journal Article Journal of proteome research · September 2012 Selected reaction monitoring mass spectrometry is an emerging targeted proteomics technology that allows for the investigation of complex protein samples with high sensitivity and efficiency. It requires extensive knowledge about the sample for the many pa ... Full text Cite

Computation of mutual information from Hidden Markov Models.

Journal Article Computational biology and chemistry · December 2010 Understanding evolution at the sequence level is one of the major research visions of bioinformatics. To this end, several abstract models--such as Hidden Markov Models--and several quantitative measures--such as the mutual information--have been introduce ... Full text Cite